Deep CORAL: Correlation Alignment for Deep Domain Adaptation

2016/07/06 by Baochen Sun, Kate Saenko, Sun, Baochen +1 · 85 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Cancer-related molecular mechanisms research #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.1607.01719

openalex publication_date 2016/07/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed to compensate for the degradation in performance due to domain shift. In this paper, we address the case when the target domain is unlabeled, requiring unsupervised adaptation. CORAL is a "frustratingly easy" unsupervised domain adaptation method that aligns the second-order statistics of the source and target distributions with a linear transformation. Here, we extend CORAL to learn a nonlinear transformation that aligns correlations of layer activations in deep neural networks (Deep CORAL). Experiments on standard benchmark datasets show state-of-the-art performance.

Citations

• Deep Domain Confusion: Maximizing for Domain Invariance

Cited by

• Le Cam Distortion: A Decision-Theoretic Framework for Robust Transfer Learning
• Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
• StegaFFD: Privacy-preserving Face Forgery Detection via Fine-grained Steganographic Domain Lifting
• Domain Adaptation in Structural Health Monitoring of Civil Infrastructure: A Systematic Review
• Self-Ensemble Post Learning for Noisy Domain Generalization
• Variance Matters: Improving Domain Adaptation via Stratified Sampling
• Neural Coherence : Find higher performance to out-of-distribution tasks from few samples
• Feature-aware Modulation for Learning from Temporal Tabular Data
• Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition
• Distilling Cross-Modal Knowledge via Feature Disentanglement
• DUPLE: An Intelligent Cross-Deployment Recognition Framework for Fiber-Optic Perimeter Security under Scarce Target Labels
• AngioDG: Interpretable Channel-informed Feature-modulated Single-source Domain Generalization for Coronary Vessel Segmentation in X-ray Angiography
• Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines
• Passive Dementia Screening via Facial Temporal Micro-Dynamics Analysis of In-the-Wild Talking-Head Video
• D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces
• Boomda: Balanced Multi-objective Optimization for Multimodal Domain Adaptation
• Saliency-Guided Domain Adaptation for Left-Hand Driving in Autonomous Steering
• Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
• Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
• ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction
• Deep causal representation learning for unsupervised domain adaptation
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Characterizing and Avoiding Negative Transfer
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization
• Environment Inference for Learning Generalizable Dynamical System
• Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization
• Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
• Robust Cross-Domain Adaptation in Texture Features Transferring for Wood Chip Moisture Content Prediction
• Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective
• Measure-Theoretic Anti-Causal Representation Learning
• Geometric Moment Alignment for Domain Adaptation via Siegel Embeddings
• Universal Adaptive Environment Discovery
• Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
• Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss
• Visual Domain Adaptation with Manifold Embedded Distribution Alignment
• Domain Conditioned Adaptation Network
• Revisiting Mixout: An Overlooked Path to Robust Finetuning
• High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
• Domain Generalization Under Posterior Drift
• Technical note on Fisher Information for Robust Federated Cross-Validation
• Robust Context-Aware Object Recognition
• Signal Classification Recovery Across Domains Using Unsupervised Domain Adaptation
• FedDAPL: Toward Client-Private Generalization in Federated Learning
• Multi-Level Heterogeneous Knowledge Transfer Network on Forward Scattering Center Model for Limited Samples SAR ATR
• Temporal Generalization: A Reality Check
• Evaluation Protocols and Cross-Subject Generalization in EEG Emotion Recognition
• Recognition and Label-Free Adaptation Across Recording Sessions in Surface-EMG Gesture Decoding
• PerturbMap: Cross-Context Transfer of Single-Cell Perturbation Responses
• More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility
• Associative Partial Domain Adaptation
• Uniform Priors for Data-Efficient Transfer
• Causal Generative Domain Adaptation Networks
• Overview of PlantCLEF 2021: cross-domain plant identification
• A review of Recent Techniques for Person Re-Identification
• CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalization
• Lost in Translation? Vocabulary Alignment for Source-Free Adaptation in Open-Vocabulary Semantic Segmentation
• Class-Invariant Test-Time Augmentation for Domain Generalization
• Importance-Weighted Domain Adaptation for Sound Source Tracking
• Multi-modal Knowledge Decomposition based Online Distillation for Biomarker Prediction in Breast Cancer Histopathology
• Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery
• Preserving Domain Generalization in Fine-Tuning via Joint Parameter Selection
• Few-Shot Adversarial Domain Adaptation
• ACE and Diverse Generalization via Selective Disagreement
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Single Domain Generalization in Diabetic Retinopathy: A Neuro-Symbolic Learning Approach
• STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach
• Generative AI for Enhanced Wildfire Detection: Bridging the Synthetic-Real Domain Gap
• Domain Adaptation via Feature Refinement
• MATL-DC: A Multi-domain Aggregation Transfer Learning Framework for EEG Emotion Recognition with Domain-Class Prototype under Unseen Targets
• AdaRNN: Adaptive Learning and Forecasting of Time Series
• Associative Domain Adaptation
• Domain Adaptation Techniques for Natural and Medical Image Classification
• Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data
• Multi-source Multimodal Progressive Domain Adaption for Audio-Visual Deception Detection
• MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training
• In Search of Lost Domain Generalization
• How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy
• SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation
• Unsupervised Pairwise Learning Optimization Framework for Cross-Corpus EEG-Based Emotion Recognition Based on Prototype Representation
• Consensus-Driven Active Model Selection
• Learning from Heterogeneous Structural MRI via Collaborative Domain Adaptation for Late-Life Depression Assessment
• Generalized few-shot transfer learning architecture for modeling the EDFA gain spectrum
• From Entanglement to Alignment: Representation Space Decomposition for Unsupervised Time Series Domain Adaptation

Related

• Correlation Alignment for Unsupervised Domain Adaptation
• Return of Frustratingly Easy Domain Adaptation
• Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
• Co-regularized Alignment for Unsupervised Domain Adaptation
• A Strategy for Label Alignment in Deep Neural Networks